Page 100 -

4.1 Linear Discriminants 87

.2776

Figure 4.10. Decision function coefficients for the two classes of cork stoppers
with features N and PRT10.

The pooled covariance matrix of the data is:

Substituting C-' in formula (4-5c), the reader can verify the results shown in
Figure 4.10.

Figure 4.11. Mahalanobis linear discriminant (solid line) for the two classes of
cork stoppers.

It is also straightforward to compute c-'(rnl-mz) = [O.l8 -0.3761'. The
orthogonal line to this vector with slope 0.4787 and passing through the middle
point between the means is shown with a solid line in Figure 4.1 1. As expected, the